Create app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,152 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import time
|
| 2 |
+
import hashlib
|
| 3 |
+
import hmac
|
| 4 |
+
import base64
|
| 5 |
+
import requests
|
| 6 |
+
import gradio as gr
|
| 7 |
+
import urllib.request
|
| 8 |
+
import urllib.parse
|
| 9 |
+
import json
|
| 10 |
+
import pandas as pd
|
| 11 |
+
from concurrent.futures import ThreadPoolExecutor
|
| 12 |
+
import os
|
| 13 |
+
import tempfile
|
| 14 |
+
from datetime import datetime
|
| 15 |
+
|
| 16 |
+
BASE_URL = "https://api.searchad.naver.com"
|
| 17 |
+
API_KEY = "010000000046604df3a0f6abf4c52824e0d5835c5cbeae279ced8b2bb9007b3cc566b190c7"
|
| 18 |
+
SECRET_KEY = "AQAAAABGYE3zoPar9MUoJODVg1xczNEcSuIBi66wWUy4p4gs/Q=="
|
| 19 |
+
CUSTOMER_ID = 2666992
|
| 20 |
+
|
| 21 |
+
class NaverAPI:
|
| 22 |
+
def __init__(self, base_url, api_key, secret_key, customer_id):
|
| 23 |
+
self.base_url = base_url
|
| 24 |
+
self.api_key = api_key
|
| 25 |
+
self.secret_key = secret_key
|
| 26 |
+
self.customer_id = customer_id
|
| 27 |
+
|
| 28 |
+
def generate_signature(self, timestamp, method, path):
|
| 29 |
+
sign = f"{timestamp}.{method}.{path}"
|
| 30 |
+
signature = hmac.new(self.secret_key.encode('utf-8'), sign.encode('utf-8'), hashlib.sha256).digest()
|
| 31 |
+
return base64.b64encode(signature).decode('utf-8')
|
| 32 |
+
|
| 33 |
+
def get_timestamp(self):
|
| 34 |
+
return str(int(time.time() * 1000))
|
| 35 |
+
|
| 36 |
+
def get_headers(self, method, uri):
|
| 37 |
+
timestamp = self.get_timestamp()
|
| 38 |
+
headers = {
|
| 39 |
+
'Content-Type': 'application/json; charset=UTF-8',
|
| 40 |
+
'X-Timestamp': timestamp,
|
| 41 |
+
'X-API-KEY': self.api_key,
|
| 42 |
+
'X-Customer': str(self.customer_id),
|
| 43 |
+
'X-Signature': self.generate_signature(timestamp, method, uri),
|
| 44 |
+
}
|
| 45 |
+
return headers
|
| 46 |
+
|
| 47 |
+
def get_keywords_data(self, keywords):
|
| 48 |
+
uri = "/keywordstool"
|
| 49 |
+
method = "GET"
|
| 50 |
+
query = {
|
| 51 |
+
'hintKeywords': ','.join(keywords),
|
| 52 |
+
'showDetail': 1
|
| 53 |
+
}
|
| 54 |
+
headers = self.get_headers(method, uri)
|
| 55 |
+
response = requests.get(self.base_url + uri, headers=headers, params=query)
|
| 56 |
+
response.raise_for_status() # HTTP ์ค๋ฅ ๋ฐ์ ์ ์์ธ ๋ฐ์
|
| 57 |
+
return response.json()
|
| 58 |
+
|
| 59 |
+
def get_blog_count(keyword):
|
| 60 |
+
client_id = "421ZKFMM5TS1xmvsF7C0"
|
| 61 |
+
client_secret = "h47UQHAOGV"
|
| 62 |
+
encText = urllib.parse.quote(keyword)
|
| 63 |
+
url = "https://openapi.naver.com/v1/search/blog?query=" + encText
|
| 64 |
+
request = urllib.request.Request(url)
|
| 65 |
+
request.add_header("X-Naver-Client-Id", client_id)
|
| 66 |
+
request.add_header("X-Naver-Client-Secret", client_secret)
|
| 67 |
+
response = urllib.request.urlopen(request)
|
| 68 |
+
rescode = response.getcode()
|
| 69 |
+
if rescode == 200:
|
| 70 |
+
response_body = response.read()
|
| 71 |
+
data = json.loads(response_body.decode('utf-8'))
|
| 72 |
+
return data['total']
|
| 73 |
+
else:
|
| 74 |
+
return 0
|
| 75 |
+
|
| 76 |
+
def get_keywords_data_chunk(chunk):
|
| 77 |
+
api = NaverAPI(BASE_URL, API_KEY, SECRET_KEY, CUSTOMER_ID)
|
| 78 |
+
return api.get_keywords_data(chunk)
|
| 79 |
+
|
| 80 |
+
def get_blog_count_parallel(keyword):
|
| 81 |
+
return (keyword, get_blog_count(keyword))
|
| 82 |
+
|
| 83 |
+
def get_monthly_search_volumes(keywords):
|
| 84 |
+
all_data = []
|
| 85 |
+
chunk_size = 10 # ํค์๋๋ฅผ 10๊ฐ์ฉ ๋๋์ด ์์ฒญ
|
| 86 |
+
|
| 87 |
+
# API ๋ณ๋ ฌ ์์ฒญ
|
| 88 |
+
with ThreadPoolExecutor(max_workers=5) as executor:
|
| 89 |
+
futures = [executor.submit(get_keywords_data_chunk, keywords[i:i+chunk_size]) for i in range(0, len(keywords), chunk_size)]
|
| 90 |
+
for future in futures:
|
| 91 |
+
data = future.result()
|
| 92 |
+
if 'keywordList' in data:
|
| 93 |
+
all_data.extend(data['keywordList'])
|
| 94 |
+
|
| 95 |
+
if not all_data:
|
| 96 |
+
return [("Error", "No data returned or invalid response from API", "", "", "")] # ๋ธ๋ก๊ทธ ๋ฌธ์ ์ ์นผ๋ผ ์ถ๊ฐ
|
| 97 |
+
|
| 98 |
+
results = []
|
| 99 |
+
unique_keywords = set()
|
| 100 |
+
for item in all_data:
|
| 101 |
+
keyword = item['relKeyword']
|
| 102 |
+
if keyword not in unique_keywords:
|
| 103 |
+
unique_keywords.add(keyword)
|
| 104 |
+
monthly_pc = item['monthlyPcQcCnt']
|
| 105 |
+
monthly_mobile = item['monthlyMobileQcCnt']
|
| 106 |
+
|
| 107 |
+
if isinstance(monthly_pc, str):
|
| 108 |
+
monthly_pc = int(monthly_pc.replace(',', '').replace('< 10', '0'))
|
| 109 |
+
if isinstance(monthly_mobile, str):
|
| 110 |
+
monthly_mobile = int(monthly_mobile.replace(',', '').replace('< 10', '0'))
|
| 111 |
+
|
| 112 |
+
total_searches = monthly_pc + monthly_mobile
|
| 113 |
+
results.append((keyword, monthly_pc, monthly_mobile, total_searches))
|
| 114 |
+
|
| 115 |
+
if len(results) >= 100:
|
| 116 |
+
break
|
| 117 |
+
|
| 118 |
+
# ๋ธ๋ก๊ทธ ๋ฌธ์ ์ ๋ณ๋ ฌ ์์ฒญ
|
| 119 |
+
with ThreadPoolExecutor(max_workers=5) as executor:
|
| 120 |
+
blog_futures = [executor.submit(get_blog_count_parallel, result[0]) for result in results]
|
| 121 |
+
for i, future in enumerate(blog_futures):
|
| 122 |
+
keyword, blog_count = future.result()
|
| 123 |
+
results[i] = (results[i][0], results[i][1], results[i][2], results[i][3], blog_count)
|
| 124 |
+
|
| 125 |
+
return results
|
| 126 |
+
|
| 127 |
+
def save_to_excel(results, keyword):
|
| 128 |
+
df = pd.DataFrame(results, columns=["ํค์๋", "PC์๊ฒ์๋", "๋ชจ๋ฐ์ผ์๊ฒ์๋", "ํ ํ์๊ฒ์๋", "๋ธ๋ก๊ทธ๋ฌธ์์"])
|
| 129 |
+
now = datetime.now().strftime('%Y-%m-%d')
|
| 130 |
+
sanitized_keyword = keyword.replace(' ', '_')
|
| 131 |
+
filename = f"{now}_{sanitized_keyword}_์ฐ๊ด๊ฒ์์ด.xlsx"
|
| 132 |
+
file_path = os.path.join(tempfile.gettempdir(), filename)
|
| 133 |
+
df.to_excel(file_path, index=False)
|
| 134 |
+
return file_path
|
| 135 |
+
|
| 136 |
+
def display_search_volumes(keywords):
|
| 137 |
+
keyword_list = [keyword.strip() for keyword in keywords.split(',')]
|
| 138 |
+
results = get_monthly_search_volumes(keyword_list)
|
| 139 |
+
file_path = save_to_excel(results, keywords)
|
| 140 |
+
return results, file_path
|
| 141 |
+
|
| 142 |
+
iface = gr.Interface(
|
| 143 |
+
fn=display_search_volumes,
|
| 144 |
+
inputs=gr.Textbox(placeholder="ํค์๋๋ฅผ ์
๋ ฅํ์ธ์"),
|
| 145 |
+
outputs=[
|
| 146 |
+
gr.Dataframe(headers=["ํค์๋", "PC์๊ฒ์๋", "๋ชจ๋ฐ์ผ์๊ฒ์๋", "ํ ํ์๊ฒ์๋", "๋ธ๋ก๊ทธ๋ฌธ์์"]),
|
| 147 |
+
gr.File(label="๋ค์ด๋ก๋ ์์
ํ์ผ")
|
| 148 |
+
],
|
| 149 |
+
title="๋ค์ด๋ฒ ์๊ฒ์๋ ๊ฒ์๊ธฐ",
|
| 150 |
+
)
|
| 151 |
+
|
| 152 |
+
iface.launch()
|